Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition
This addresses security risks in gait recognition systems used for social security, but it is incremental as it builds on existing adversarial attack methods.
The paper tackles the vulnerability of state-of-the-art sequence-based gait recognition models to adversarial attacks by proposing a temporal sparse adversarial attack method that uses a GAN to generate high-quality adversarial frames, resulting in a dramatic accuracy drop when only one-fortieth of frames are attacked.
Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and spatial information. However, their robustness under adversarial attacks has not been clearly explored. In this paper, we demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks. To this end, we propose a novel temporal sparse adversarial attack method. Different from previous additive noise models which add perturbations on original samples, we employ a generative adversarial network based architecture to semantically generate adversarial high-quality gait silhouettes or video frames. Moreover, by sparsely substituting or inserting a few adversarial gait silhouettes, the proposed method ensures its imperceptibility and achieves a high attack success rate. The experimental results show that if only one-fortieth of the frames are attacked, the accuracy of the target model drops dramatically.